Choose the diarizing model
Select GPT-4o Transcribe Diarize and add your own OpenAI API key. This is an optional cloud model: the recording is sent directly to OpenAI for transcription.
Meeting recording · macOS
Record & transcribe meetings
on your Mac. Free.
Capture your mic and the call’s system audio together. Transcribe locally by default, or choose optional cloud speaker labels — without a bot joining the meeting.
VoiceToText records Zoom, Google Meet, Microsoft Teams, FaceTime, or any call playing through your Mac, keeps running in the background while you work, and transcribes everything locally on the Apple Neural Engine by default — saved to your on-device history.
How it captures the call
Both sides of the conversation — without a bot in the meeting.
Most meeting tools join your call as a participant. VoiceToText doesn’t. It records locally from macOS itself: your microphone plus the system audio coming out of your Mac, mixed into one recording.
Start a recording from the Conversations pane, then carry on. VoiceToText streams the audio straight to disk in the background — no RAM bloat, no window to babysit — and transcribes it the moment you stop, on-device by default. It works with whatever is making sound:
- Zoom
- Google Meet
- Microsoft Teams
- FaceTime
- Webex
- Slack huddles
- Discord
- Any audio
Speaker 1: Let's kick off the weekly sync.
Speaker 2: Design is signed off, and
the team is on the last endpoint.
Speaker 1: Any blockers before Friday?
Speaker 2: None. I'll send the notes
right after this call.Speaker diarization
Separate speakers, then give the labels real names.
Local Whisper and Parakeet models produce a standard transcript. When you need to distinguish speakers, the optional GPT-4o Transcribe Diarize model adds labeled turns that you can rename.
See who said what
The transcript is split into turns labeled Speaker 1, Speaker 2, and so on, instead of one uninterrupted block of meeting text.
Replace labels with names
Open Name speakers on the saved recording and assign display names. Those names appear when you view or copy the transcript and persist across transcript versions.
Three steps
How to record a meeting on your Mac.
- 01
Start recording
Open Conversations in VoiceToText and click Start Recording. The first time, macOS asks once for Microphone and Screen Recording — that's what lets it hear you and capture system audio.
- 02
Keep working
It records in the background, streaming straight to disk. Switch apps, take notes, share your screen — the recording keeps running with barely any footprint.
- 03
Stop → transcript
Stop, and the recording is transcribed with your chosen model — on-device by default, long calls in segments — and saved to your history with the audio you can replay and a transcript you can copy.
What you get
A full meeting recorder, built into your dictation app.
No second app subscription and no plugin in the call. Choose a local model to keep transcription on your Mac, or explicitly select a cloud provider when you want one of its features.
Mic + system audio
Records both directions at once through ScreenCaptureKit, so everyone on the call is captured — not just your side.
Private by default
Local models transcribe the recording on your Mac. With a local engine, your audio never leaves the device — transcription makes zero network calls.
A history you can replay
Recordings are saved on-device with audio and transcript — a rolling history of your 200 most recent. Play back, copy, favorite; deletes come with an undo, and a crash-interrupted recording is recovered on the next launch.
Regenerate & compare
Re-run the transcript with a more accurate model and keep both versions side by side, so you can pick the better one and drop the other.
Import a file
Already have a recording? Drop in any audio or video file — VoiceToText extracts the audio and transcribes it the same way.
No bot, no app subscription
Nothing joins your call, and VoiceToText does not charge by the minute. Local transcription has no provider fee; optional cloud providers may charge under your API key.
Permissions & privacy
Local transcription keeps your meetings on your Mac.
Recording a conversation is sensitive, so VoiceToText keeps it local by default. Here is exactly what it needs and where your audio goes.
- Microphone records your voice; Screen Recording is how macOS exposes system audio through ScreenCaptureKit — VoiceToText never records the screen, only the audio. Accessibility is only used by dictation, not by meeting recording.
- With a local model (Whisper or Parakeet on the Apple Neural Engine), the recording is transcribed entirely on your Mac and never leaves the device.
- Cloud transcription is opt-in: only if you pick an OpenAI or ElevenLabs model is audio sent — directly to that provider under your own API key. Speaker diarization specifically uses OpenAI GPT-4o Transcribe Diarize. VoiceToText is never in that path.
- Recordings and transcripts live in Application Support on your Mac. Delete any of them anytime, right from the history — with a 5-second undo if you slip.
FAQ
Recording meetings on Mac — common questions.
Can I record and transcribe meetings on my Mac for free?
Yes. VoiceToText is free, with source available on GitHub and no app subscription or per-minute app fee. Local transcription has no provider charge; optional cloud models may charge usage under your own API key. The same app also does hotkey dictation into any text field.
Does it record the other participants, or just my microphone?
Both. VoiceToText captures your microphone and your Mac's system audio at the same time, so the people on the other end of a Zoom, Google Meet, Microsoft Teams, FaceTime, Webex, or Discord call are recorded along with you. System-audio capture uses Apple's ScreenCaptureKit, so it works with any app that plays sound — no meeting-specific plugin or bot in the call.
Can VoiceToText identify and label different speakers?
Yes, with the optional GPT-4o Transcribe Diarize model. It separates the transcript into turns labeled Speaker 1, Speaker 2, and so on; you can rename those labels in the recording history, and the names are used when you view or copy the transcript. Diarization is a cloud-only OpenAI feature: it requires your own OpenAI API key and sends the recording directly to OpenAI. Local Whisper and Parakeet models do not separate speakers.
Is meeting recording private? Does my audio stay on my Mac?
Yes. With a local model (Whisper or Parakeet on the Apple Neural Engine) the recording is transcribed entirely on-device and never leaves your Mac. The audio file and transcript are saved to a local history under Application Support. Cloud transcription is strictly opt-in: only if you choose an OpenAI or ElevenLabs model is audio sent — directly to that provider under your own API key.
Which permissions does meeting recording need?
Two: Microphone (to record your voice) and Screen Recording (which is how macOS exposes system audio through ScreenCaptureKit — VoiceToText never records the screen, only the audio). Accessibility is only used by the dictation feature (typing at the cursor, the global shortcut, Esc to cancel) and is not needed to record meetings. You grant these once in System Settings and can revoke them anytime.
What happens with long meetings — or if the app crashes mid-recording?
Long recordings are split into segments at the quietest moments and transcribed piece by piece with progress shown, so an hour-long call transcribes reliably. The audio streams straight to disk while recording, and if the app is interrupted — crash, force-quit, power loss — the recording is repaired and filed into your history on the next launch, so a long recording isn't lost.
Can I transcribe an existing audio or video file?
Yes. Open Conversations and choose Upload File to drop in an existing recording — audio or video, in any common format. VoiceToText extracts the audio track, transcribes it on-device, and saves it to your history alongside your live recordings.
Can I re-transcribe a recording with a more accurate model?
Yes. Every recording keeps its audio, so you can regenerate the transcript with a different engine — for example switch from fast on-device Parakeet to OpenAI GPT-4o Transcribe for a tricky recording. The new transcript becomes active and the previous one is kept as an alternate, so you can compare both and remove whichever you don't want.
Ready to record
Start recording your meetings — free.
One DMG, drag to Applications, grant Microphone and Screen Recording. Then record any call and get an on-device transcript.
The same app also does hotkey dictation into any text field. See everything VoiceToText does →